claude-agent-team

Shared CAST conventions for all agents. Loaded automatically via agent frontmatter.

Execute a CAST plan by reading the Agent Dispatch Manifest and dispatching agents in dependency order — parallel batches simultaneously, sequential batches one at a time. Pass a plan file path, 'next' for the most recent plan, or 'resume' to continue from a checkpoint.

Full CAST agent registry with model assignments. Load when building an Agent Dispatch Manifest, orchestrating multi-agent workflows, or when you need to verify which model a specific agent runs on.

Comprehensive CAST codebase audit — bugs, security, performance, test coverage. Dispatches 4 parallel researchers to scan the codebase and collates findings into a dated report. Manual invocation only; monthly scheduling is a design intention (helper not yet shipped).

Assemble morning briefing sections into a structured markdown file. Use when writing the final briefing output after all data sources have been gathered.

Activate careful mode — require explicit confirmation before any Write, Edit, or Bash operations. Use when working on production code or sensitive systems.

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report. When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.

Freeze mode — read-only session, no file modifications allowed. Use for exploration, research, or review-only sessions.

Scan project repositories for yesterday's git activity. Use when summarizing development progress for briefings, reports, standups, or when user asks "what did I work on yesterday" or "recent commits".

Terse output mode. Compresses Claude prose to minimum tokens while preserving technical accuracy. Three intensity levels: lite, full (default), ultra.

Git merge, rebase, and conflict resolution specialist. Use when merging feature branches, rebasing onto main, resolving merge conflicts, merging PRs via gh CLI, or cleaning up merged worktrees and branches. Hard-blocks force-merges to main/master without explicit approval.

Activate the heavy planner→/orchestrate chain — write a structured plan file with Agent Dispatch Manifest, then invoke the /orchestrate skill to execute it in waves. Reserve for genuinely multi-file / multi-hour / multi-agent work (large refactors, migrations, features spanning many files). For single-session-sized work (one or a few files), use built-in plan mode (shift-tab) instead — not this skill.

Python and shell-script conventions for CAST projects. Load when writing, reviewing, or debugging Python scripts, hook scripts, or files under scripts/ or bin/. Covers stdlib-only policy, DB access patterns, exit codes, idempotency, stdin parsing, and hook script conventions.

Full tech stack reference and dev command cheatsheet. Load when you need to look up exact package names, commands, or project paths.

TypeScript and React coding conventions for CAST projects. Load when writing, reviewing, or debugging TypeScript/TSX/React code. Covers file naming, type patterns, hooks, component conventions, and testing approach.

Multi-step workflow with human-approval gates before destructive operations. Use when a task involves irreversible actions like mass file writes, database migrations, git force-push, dependency removal, or infrastructure changes.

Full project catalog — project paths, stacks, remotes, and runtime paths. Load when you need a project's path, remote, stack, or build/deploy specifics.

Full tech stack reference and dev command cheatsheet. Load when you need to look up exact package names, commands, or project paths.